INDEX

Explanations

repetitive or syntactical structures using "as"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.20

lero

-0.17

-0.16

umber

-0.15

åĭ

-0.15

ammers

-0.14

oust

-0.14

ucci

-0.14

oub

-0.14

avers

-0.14

POSITIVE LOGITS

IMS

0.17

 regards

0.17

TabIndex

0.15

 indeed

0.15

 Charg

0.14

è¯´è¯Ŀ

0.14

 elsewhere

0.14

TRL

0.14

 distinct

0.14

//{{

0.14

Activations Density 0.151%

repetitive or syntactical structures using "as"

No Comments

No Known Activations